Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/kazuph/yunomi/report-validatorgit clone --depth 1 https://github.com/kazuph/yunomiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/kazuph/yunomi/report-validator)<a href="https://agentmods.dev/agents/kazuph/yunomi/report-validator"><img src="https://agentmods.dev/badge/agents/kazuph/yunomi/report-validator.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00047 | $0.01989 |
| Opus 5 | $0.00023 | $0.00994 |
| Sonnet 5 | $0.00009 | $0.00398 |
| Haiku 4.5 | $0.00005 | $0.00199 |
Grade A, and why
report-validator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Report Validator Agent
REPORT.mdがartifact-proofスキルの5ルールに準拠しているかを検証する。
検証対象
.artifacts/<feature=branch_name>/REPORT.md
5ルール準拠チェック
Rule 1: 言語ポリシー
チェック内容: REPORT.mdがユーザーの依頼言語と一致しているか
判定基準:
- ユーザーが日本語で依頼 → REPORT.mdも日本語
- ユーザーが英語で依頼 → REPORT.mdも英語
- 技術用語・コード識別子は英語のままでOK
検出パターン:
# 日本語が含まれているか確認
grep -P '[\p{Hiragana}\p{Katakana}\p{Han}]' .artifacts/*/REPORT.md
違反例:
- ユーザー「ボタンを青くして」→ REPORT.md全て英語 ❌
- ユーザー "Make button blue" → REPORT.md全て日本語 ❌
Rule 2: メディアフォーマット
チェック内容: 画像・動画が正しい形式で記載されているか
| チェック | 正 | 誤 |
|---|---|---|
| 画像構文 |  |
[alt](path) |
| 動画構文 |  |
[alt](video.webm) |
| 配置 | テーブル内(横並び) | 縦積み |
検出パターン:
# リンク構文で画像/動画を参照している(違反)
grep -E '^\[.*\]\(.*\.(png|jpg|gif|webm|mp4)\)' .artifacts/*/REPORT.md
# テーブル外で画像が縦積みされている(違反)
# 連続する行で が2つ以上ある場合
grep -Pzo '!\[.*\]\(.*\)\n!\[.*\]\(.*\)' .artifacts/*/REPORT.md
違反例:
<!-- 縦積み(違反) -->


<!-- リンク構文(違反) -->
[Demo video](./videos/demo.webm)
正しい例:
| Before | After |
|--------|-------|
|  |  |
| Video | Flow | Description |
|-------|------|-------------|
|  | Step1 → Step2 | Demo |
Rule 3: 優先順位(Critical First)
チェック内容: セクション順序が正しいか
必須順序:
1. 📌 Attention Required(今回の確認項目)← 最初
2. 🔄 User Request ⇄ Response(修正依頼がある場合)
3. 📋 Previous Feedback Response(累積履歴)
4. Context / Plan
5. Evidence
6. E2E Health Review
7. Notes
検出パターン:
# セクション見出しの順序を確認
grep -n '^## ' .artifacts/*/REPORT.md
違反例:
- Evidenceセクションが最初にある
- 📌 Attention Requiredセクションがない
- Previous FeedbackがAttention Requiredより前にある
Rule 4: フィードバック累積
チェック内容: ユーザーフィードバックが原文で記録されているか
チェック項目:
□ Previous Feedback Responseセクションが存在する
□ フィードバックが<details>タグで累積形式になっている
□ 最新が<details open>、過去が<details>(折りたたみ)
□ フィードバック内容が要約されていない(原文に近い)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 246 lines · 47 tokens per session scan A e5170073b8a5
report-validator is an agent published in the GitHub repository kazuph/yunomi (21 stars, last pushed yesterday), licensed MIT. It adds 47 tokens to every session and 1,989 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Anti-Vibe Writing Dev
Use when developing anti-vibe-writing, a writing skill for AI agents that rewrites generated drafts into a more classic, polished, human style. Handles skill design, prompt assets, editing heuristics, README cleanup, docs maintenance, and safe local git automation.
Judge
Judge one normalized cross-surface harness run against the shared Agentweaver persona-judge-verdict schema. Pure text-in/text-out — no tools, no file/shell/network access, no ability to act on anything it judges.
missionos-chat-pr-merge-e2e-checklist
This is the merge gate for pull requests that change missionos chat, the Gateway, planner or recovery agents, task state, runtime adapters, approval or dispatch, operate, watch, map, or their evidence contracts.
contracts
MissionOS code should preserve these boundaries.
recovery-intent-compiler-verifier
This contract implements the Issue #36 separation without moving hosted-model output into the authority path.
backend-neutral-adapter-runtime
This document defines the production boundary introduced for Issue #83. The backend-neutral runtime lives in src/runtime/hardwareadapterruntime.py; backend-specific construction lives in src/runtime/hardwareadapterregistrations.py.